And some 1.0 releases of the Multiforcer

[Bitweasil]

http://cryptohaze.com/multiforcer.php

Download links should work.

Testing/reviews welcome!

Known bugs:
- Network support is glitchy on password change - sometimes the clients don't get the memo that the password length has changed. Known, being worked on.
- Network support doesn't handle salted hashes yet.
- Network server on Windows may crash when a client disconnects.

... network support works, but is glitchy.

Otherwise, all is good to go

[Picch]

Working good for me in Linux...GPU0: GTX580, GPU1: GTX280

Code: Select all

/Cryptohaze-Multiforcer -h NTLM -f hash.txt --min=1 --max=7 -l -c charsets/charset-all-multi -m 1000 --threads 512 --blocks 240 --bits 34 -o output.txt --notfoundfile=notfound.txt

Code: Select all

+----------------------------------------------------------------------------------------------------+
|'p' to pause                         Cryptohaze Multiforcer 1.00                        'q' to quit |
|                                          Mode: Standalone                                          |
|Hash type     :      NTLM |                Passwords Found                  |                       |
|Current PW len:         6 |                                                 |  0: GPU: 1950.31M/s   |
|Total hashes  :         6 |  GPGPU                                          |  1: GPU: 774.79M/s    |
|Cracked hashes:         8 |  G0o|)                                          |                       |
|Total time    : 00:01:16  |  GoOd!                                          |                       |
|WUs: 9/43 (20.9%)         |  Bwah                                           |                       |
|                          |  1234                                           |                       |
|--------------------------|  P4s$                                           |                       |
| Thread 1 mem loaded      |  abc                                            |                       |
| Thread 0 mem loaded      |  bad                                            |                       |
| Creating 2 threads       |                                                 |                       |
| Starting pw len 6        |             ┌──────────────────┐                |                       |
| Threads joined           |             │      PAUSED      │                |                       |
| Td 0: out of WU.         |             │  Press any key   │                |                       |
| Td 1: out of WU.         |             └──────────────────┘                |                       |
| Thread 1 mem loaded      |                                                 |                       |
| Thread 0 mem loaded      |                                                 |                       |
| Creating 2 threads       |                                                 |                       |
| Starting pw len 5        |                                                 |                       |
| Threads joined           |                                                 |                       |
| Td 0: out of WU.         |                                                 |                       |
| Td 1: out of WU.         |                                                 |                       |
| Thread 1 mem loaded      |                                                 |                       |
| Thread 0 mem loaded      |                                                 |                       |
| Creating 2 threads       |                                                 |                       |
| Starting pw len 4        |                                                 |                       |
| Threads joined           |                                                 |                       |
| Td 0: out of WU.                                                             TOTAL: 2725.09M/s     |
|                                                                                                    |
+----------------------------------------------------------------------------------------------------+


Code: Select all

/Cryptohaze-Multiforcer -h MD5 -f hash.txt --min=1 --max=7 -l -c charsets/charset-all-multi -m 1000 --threads 512 --blocks 240 --bits 34 -o output.txt --notfoundfile=notfound.txt

Code: Select all

+----------------------------------------------------------------------------------------------------+
|'p' to pause                         Cryptohaze Multiforcer 1.00                        'q' to quit |
|                                          Mode: Standalone                                          |
|Hash type     :       MD5 |                Passwords Found                  |                       |
|Current PW len:         6 |                                                 |  0: GPU: 1288.63M/s   |
|Total hashes  :        14 |                                                 |  1: GPU: 550.06M/s    |
|Cracked hashes:         0 |                                                 |                       |
|Total time    : 00:01:09  |                                                 |                       |
|WUs: 4/43 (9.3%)          |                                                 |                       |
|                          |                                                 |                       |
|--------------------------|                                                 |                       |
| Thread 0 mem loaded      |                                                 |                       |
| Thread 1 mem loaded      |                                                 |                       |
| Creating 2 threads       |                                                 |                       |
| Starting pw len 6        |             ┌──────────────────┐                |                       |
| Threads joined           |             │      PAUSED      │                |                       |
| Td 1: out of WU.         |             │  Press any key   │                |                       |
| Td 0: out of WU.         |             └──────────────────┘                |                       |
| Thread 0 mem loaded      |                                                 |                       |
| Thread 1 mem loaded      |                                                 |                       |
| Creating 2 threads       |                                                 |                       |
| Starting pw len 5        |                                                 |                       |
| Threads joined           |                                                 |                       |
| Td 1: out of WU.         |                                                 |                       |
| Td 0: out of WU.         |                                                 |                       |
| Thread 0 mem loaded      |                                                 |                       |
| Thread 1 mem loaded      |                                                 |                       |
| Creating 2 threads       |                                                 |                       |
| Starting pw len 4        |                                                 |                       |
| Threads joined                                                               TOTAL: 1838.69M/s     |
|                                                                                                    |
+----------------------------------------------------------------------------------------------------+


PS Where are you going to be hiding at Defcon? I get into Vegas Wednesday night.

[Bitweasil]

Awesome

Not sure yet where I'll be hiding... look for a guy with a scrolling LED name tag that says "Bitweasil." That'll be me... or one of several clones I keep around.

Probably check the blog - I'll try to update that if I'm hanging out anywhere for extended periods of time.

[Picch]

I'm curious about the feasibility of adding LM support. I know that almost perfect CPU based rainbow tables exist making cracking LM hashes pretty fast in small numbers. But with a large hashlist I'd be willing to bet that a simple GPU bruteforce would blow CPU based rainbow tables away.

[Bitweasil]

I'm working on a DES engine currently, both for LM and for some file encryption stuff.

As soon as it's done, I'll add in LM support. I agree about brute forcing large lists.

[Sc00bz]

One problem would be that bit slicing needs a lot of registers.

CPUs can do 256 LM hashes at once per core (with AVX [Sandy Bridge and Bulldozer Q3 2011]) and GPUs can only do 32 LM hashes at once per core.

Nvidia GPUs are what like 10-ish times faster than CPUs. So GPUs would be around 1.25 times faster. The only benefit now is being able to have multiple GPUs in one computer.

ATI is twice that so... 2.5 times faster. Ohh wait ATI will probably run out of registers so it will need to use less cores than it has.

[Picch]

I'm working on a DES engine currently, both for LM and for some file encryption stuff.

As soon as it's done, I'll add in LM support. I agree about brute forcing large lists.

Thanks, I cannot wait! I currently have large project that is in desperate need for some LM+GPU love.

[Bitweasil]

One problem would be that bit slicing needs a lot of registers.

Sadly, yes. Or efficient register spilling. Which may be useful - I'm not sure if this can be done. atom & I both keep seeing references to "fast as hell" bitsliced DES on GPUs, but neither of us can find any actual code that does it.

CPUs can do 256 LM hashes at once per core (with AVX [Sandy Bridge and Bulldozer Q3 2011]) and GPUs can only do 32 LM hashes at once per core.

AVX does not yet support integer/boolean ops. Check your sources. I wish they did, I was hoping they did, but they don't. Not until Ivy Bridge. So still 128 bit registers for hash stuff... sadly.

Nvidia GPUs are what like 10-ish times faster than CPUs. So GPUs would be around 1.25 times faster. The only benefit now is being able to have multiple GPUs in one computer.

ATI is twice that so... 2.5 times faster. Ohh wait ATI will probably run out of registers so it will need to use less cores than it has.

It's one of those "Try it & work on it" things. For now, I will be using lookup tables & shared memory. I may try for bit slicing to see if I can do it.

[Bitweasil]

Thanks, I cannot wait! I currently have large project that is in desperate need for some LM+GPU love.

I'll see what I can do in the next week or two.

[Sc00bz]

CPUs can do 256 LM hashes at once per core (with AVX [Sandy Bridge and Bulldozer Q3 2011]) and GPUs can only do 32 LM hashes at once per core.

AVX does not yet support integer/boolean ops. Check your sources. I wish they did, I was hoping they did, but they don't. Not until Ivy Bridge. So still 128 bit registers for hash stuff... sadly.

AVX does floating point and, or, xor, and andn. Which are applied to the whole 256 bits. Source some Intel AVX PDF that I read forever ago and well JtR is using this code here:

Code: Select all

/* Not __m256i because bitwise ops are "floating-point" with AVX */
typedef __m256 vtype;

#define vst(dst, ofs, src) \
   _mm256_store_ps((float *)((DES_bs_vector *)&(dst) + (ofs)), (src))

#define vxorf(a, b) \
   _mm256_xor_ps((a), (b))

#define vnot(dst, a) \
   (dst) = _mm256_xor_ps((a), *(vtype *)&DES_bs_all.ones)
#define vand(dst, a, b) \
   (dst) = _mm256_and_ps((a), (b))
#define vor(dst, a, b) \
   (dst) = _mm256_or_ps((a), (b))
#define vandn(dst, a, b) \
   (dst) = _mm256_andnot_ps((b), (a))
#define vxorn(dst, a, b) \
   (dst) = _mm256_xor_ps(_mm256_xor_ps((a), (b)), \
       *(vtype *)&DES_bs_all.ones)